Commit ·
52e294a
1
Parent(s): 9efbcaf
Update README.md
Browse files
README.md
CHANGED
|
@@ -115,6 +115,9 @@ text = tokenizer.batch_decode(outputs)[0]
|
|
| 115 |
print(text)
|
| 116 |
```
|
| 117 |
|
|
|
|
|
|
|
|
|
|
| 118 |
### Citation
|
| 119 |
```bib
|
| 120 |
@article{textbooks2,
|
|
|
|
| 115 |
print(text)
|
| 116 |
```
|
| 117 |
|
| 118 |
+
**Remark.** In the generation function, our model currently does not support beam search (`num_beams` >1) and `attention_mask' parameters.
|
| 119 |
+
Furthermore, in the forward pass of the model, we currently do not support outputing hidden states or attention values, using custom input embeddings (instead of the model's).
|
| 120 |
+
|
| 121 |
### Citation
|
| 122 |
```bib
|
| 123 |
@article{textbooks2,
|